Model comparison
Gemma 1.1 7b IT vs Llama 2-7B
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 28.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Google
MetaSummary
- They share 15 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 8 categories and Llama 2-7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 1.1 7b IT leads 19.6 to 15.1.
Side by side
| Gemma 1.1 7b IT | Llama 2-7B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.7 | 28.6 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 31.0 (#279), Llama 2-7B: 28.7 (#302)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1084 | 1002 |
| HumanEval+ | 35.4% | — |
| MBPP+ | 45% | — |
Reasoning Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 19.6 (#235), Llama 2-7B: 15.1 (#309)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1009 |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |
| Epoch Capabilities Index | — | 98.54 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 29.5 (#217), Llama 2-7B: 28.2 (#231)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Math | 1107 | 1042 |
| GSM8K | — | 16.7% |
Knowledge Too close to call
Gemma 1.1 7b IT: 27.8 (#242), Llama 2-7B: 27.7 (#243)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1039 | 1036 |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Gemma 1.1 7b IT: —, Llama 2-7B: —
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 28.3 (#268), Llama 2-7B: 23.9 (#288)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1052 | 973 |
| LMArena Chinese | 1060 | 973 |
| LMArena French | 1064 | 969 |
| LMArena German | 1054 | 978 |
| LMArena Russian | 1046 | 995 |
| LMArena Spanish | 1049 | 1007 |
| LMArena Japanese | 971 | — |
| LMArena Korean | 988 | — |
Instruction Following Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 54.3 (#278), Llama 2-7B: 51.0 (#293)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1057 | 1006 |
Long Context Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 32.0 (#267), Llama 2-7B: 30.4 (#282)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1056 | 999 |
Writing & Preference Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 30.6 (#283), Llama 2-7B: 28.1 (#293)
| Benchmark | Gemma 1.1 7b IT | Llama 2-7B |
|---|---|---|
| LMArena Text | 1094 | 1053 |
| LMArena Creative Writing | 1059 | 1033 |
| LMArena Multi-Turn | 1040 | 1029 |
Frequently asked questions
Is Gemma 1.1 7b IT better than Llama 2-7B?
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 28.6 on the Noometry Index.
Is Gemma 1.1 7b IT or Llama 2-7B better for coding?
Gemma 1.1 7b IT scores higher on coding benchmarks: 31.0 versus 28.7 in the Noometry coding category.
How many benchmarks do Gemma 1.1 7b IT and Llama 2-7B share?
15 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Llama 2-7B has 29.